US 10,896,184 B2Granted

Method and system for capturing and exploiting user intent in a conversational interaction based information retrieval system

AssigneeVeveo, Inc.

InventorsMurali Aravamudan, Sashikumar Venkataraman, Rakesh Barve, Ahmed Nizam Mohaideen Pathurudeen

Life of this patent

Estimating the term…

Loading patent…

Abstract

Systems and methods are disclosed for processing a search request received from a user. A method includes providing access to content items associated with metadata. The method includes providing information about at least one search previously performed for a user, and providing access to information describing relationships between at least one of the content items and the metadata. The method includes receiving a present input from the user intended to identify a desired content item. Upon determining that results from the previous search did not satisfy the search request from the user, the method includes determining an intent shared by the previous search and the present input based on comparing (i) the relationship information, (ii) the previous search, and (iii) the present input. The method also includes selecting and presenting a subset of content items based on comparing the shared intent and the metadata.

Claims20

Dependent claims

A method of presenting search results matching a determined user intent, the method comprising:

receiving a first search query and a second search query, wherein one of the first search query or the second search query indicates a window of time during which a user intends to view a media asset;
determining whether any media assets that match the first search query or the second search query are available in the window of time by determining whether any media assets that match the first search query or the second search query are scheduled for delivery during the window of time;
and
in response to determining that no media assets that match the first search query or the second search query are available in the window of time:
calculating one or more distances in a relationship graph between a first attribute of a first search result that matches the first search query and a second attribute of a second search result that matches the second search query;
selecting one or more connections between the first attribute and the second attribute based on the calculated distances;
generating a set of media assets based on the selected connections in the relationship graph, wherein each of the set of media assets has at least one of the first attribute or the second attribute and wherein each of the set of media assets is available within the window of time;
and
generating one or more listings for media assets of the set of media assets.

6 more elements

A system for presenting search results matching a determined user intent, the system comprising:

an electronic computing device configured to:
receive a first search query and a second search query, wherein one of the first search query or the second search query indicates a window of time during which a user intends to view a media asset;
determine whether any media assets that match the first search query or the second search query are available in the window of time by determining whether any media assets that match the first search query or the second search query are scheduled for delivery during the window of time;
and
in response to determining that no media assets that match the first search query or the second search query are available in the window of time:
calculate one or more distances in a relationship graph between a first attribute of a first search result that matches the first search query and a second attribute of a second search result that matches the second search query;
select one or more connections between the first attribute and the second attribute based on the calculated distances;
generate a set of media assets based on the selected connections in the relationship graph, wherein each of the set of media assets has at least one of the first attribute or the second attribute and wherein each of the set of media assets is available within the window of time;
and
generate one or more listings for media assets of the set of media assets.

7 more elements

A non-transitory machine-readable medium comprising non-transitory machine-readable instructions encoded thereon for presenting search results matching a determined user intent, the instructions comprising:

instructions for receiving a first search query and a second search query, wherein one of the first search query or the second search query indicates a window of time during which a user intends to view a media asset;
instructions for determining whether any media assets that match the first search query or the second search query are available in the window of time by determining whether any media assets that match the first search query or the second search query are scheduled for delivery during the window of time;
and
instructions for, in response to determining that no media assets that match the first search query or the second search query are available in the window of time:
calculating one or more distances in a relationship graph between a first attribute of a first search result that matches the first search query and a second attribute of a second search result that matches the second search query;
selecting one or more connections between the first attribute and the second attribute based on the calculated distances;
generating a set of media assets based on the selected connections in the relationship graph, wherein each of the set of media assets has at least one of the first attribute or the second attribute and wherein each of the set of media assets is available within the window of time;
and
generating one or more listings for media assets of the set of media assets.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/913,609Filed 6 Mar 2018 · continuation
Priority: 10 May 2013
Published: US 2018/0260445 A113 Sep 2018
Granted: 19 Jan 2021
Term ends: Not estimatedThe source records don’t support an estimate.

Classification3 codes

G06F 16/2457
Query processing: with adaptation to user needs
G06F 16/95
Details of database functions independent of the retrieved data types: retrieval from the web
G06F
Computing and data processing

Family

Application61/822,098Us provisional application · filed 10 May 2013
Application14/274,147Parent of this continuation · filed 9 May 2014
US 2018/0260445 A1Pre-grant publication · published 13 Sep 2018
US 9,946,757 B2Parent of this continuation
US 2014/0337381 A1Published application
US 10,896,184 B2This patent

From the US filing history. Foreign family members aren’t listed.